WO2016107474A1 - Procédé et système d'inspection de véhicule - Google Patents

Procédé et système d'inspection de véhicule Download PDF

Info

Publication number
WO2016107474A1
WO2016107474A1 PCT/CN2015/098438 CN2015098438W WO2016107474A1 WO 2016107474 A1 WO2016107474 A1 WO 2016107474A1 CN 2015098438 W CN2015098438 W CN 2015098438W WO 2016107474 A1 WO2016107474 A1 WO 2016107474A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
transmission image
image
template
image template
Prior art date
Application number
PCT/CN2015/098438
Other languages
English (en)
Chinese (zh)
Inventor
陈志强
张丽
赵自然
刘耀红
顾建平
胡峥
李强
Original Assignee
清华大学
同方威视技术股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 清华大学, 同方威视技术股份有限公司 filed Critical 清华大学
Priority to EP15875152.9A priority Critical patent/EP3115772B1/fr
Priority to MYPI2016703579A priority patent/MY190242A/en
Publication of WO2016107474A1 publication Critical patent/WO2016107474A1/fr
Priority to US15/282,134 priority patent/US10289699B2/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G06F16/5838—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using colour
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N23/00—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00
    • G01N23/02—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by transmitting the radiation through the material
    • G01N23/04—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by transmitting the radiation through the material and forming images of the material
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
    • G01V5/00—Prospecting or detecting by the use of ionising radiation, e.g. of natural or induced radioactivity
    • G01V5/20—Detecting prohibited goods, e.g. weapons, explosives, hazardous substances, contraband or smuggled objects
    • G01V5/22—Active interrogation, i.e. by irradiating objects or goods using external radiation sources, e.g. using gamma rays or cosmic rays
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/54—Browsing; Visualisation therefor
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G06T7/001—Industrial image inspection using an image reference approach
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
    • G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
    • G06T7/337—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods involving reference images or patches
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2223/00—Investigating materials by wave or particle radiation
    • G01N2223/40—Imaging
    • G01N2223/401—Imaging image processing
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2223/00—Investigating materials by wave or particle radiation
    • G01N2223/60—Specific applications or type of materials
    • G01N2223/631—Specific applications or type of materials large structures, walls
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10116—X-ray image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30248—Vehicle exterior or interior
    • G06T2207/30268—Vehicle interior
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/05—Recognition of patterns representing particular kinds of hidden objects, e.g. weapons, explosives, drugs
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/08—Detecting or categorising vehicles

Definitions

  • Embodiments of the present disclosure relate to automatic detection of suspects in a radiation image, and more particularly to a corresponding security inspection method and apparatus for detecting suspects such as prohibited or dangerous goods in a vehicle scanning system.
  • the vehicle bottom security inspection system mainly uses a digital camera to photograph the vehicle chassis. By observing the visible light image of the chassis, it is judged whether there are entrained objects in various positions of the chassis, and the security inspection in the vehicle needs to be completed by manual hand-held detectors, and the operation thereof is complicated. It is inefficient and cannot meet the fast and accurate requirements for small vehicle security.
  • X-ray detection is to form a radiation image of the whole vehicle by X-ray penetration of the whole vehicle, and assists the inspectors to find the suspect through the different degrees of X-ray penetration of different substances.
  • the present disclosure proposes a vehicle inspection method and system that can improve the efficiency and accuracy of vehicle inspection.
  • a vehicle inspection method comprising the steps of: acquiring a transmission image of a vehicle under inspection; acquiring a transmission image template of the same vehicle type as the vehicle from a database; and transmitting a transmission image of the vehicle under inspection Performing registration with the transmission image template; obtaining a difference between the registered transmission image and the registered transmission image template to obtain a variation region of the transmission image of the vehicle with respect to the transmission image template; and performing the variation region Process to determine if the vehicle carries a suspect.
  • the step of obtaining a transmission image template of the same vehicle type as the vehicle from the database comprises: The transmission image template of the vehicle model is retrieved from the database based on the unique identifier of the vehicle being inspected.
  • the step of acquiring a transmission image template of the same vehicle type from the database from the database comprises: extracting internal structural information of the vehicle from the transmission image, synthesizing external characteristic information of the vehicle, and retrieving the vehicle type from the database Transmission image template.
  • the step of registering the transmission image of the inspected vehicle and the transmission image template comprises: rigidly registering a transmission image of the inspected vehicle and the transmission image template to globally image Transform alignment; elastically registering the transmission image of the inspected vehicle and the transmission image template to eliminate local deformation.
  • the step of rigid registration comprises: performing feature extraction on two images to obtain feature points; finding matching feature point pairs by performing similarity measure; obtaining image space coordinate transformation parameters by matching feature point pairs; and transforming parameters by coordinates Perform image registration.
  • the method further comprises: normalizing the gray scales of the two images after the rigid registration before the elastic registration.
  • the method further comprises the step of removing portions of the transmission image other than the vehicle image prior to registration.
  • the method further comprises the step of labeling the suspect in the variable area.
  • a vehicle inspection system comprising: a radiation imaging system that acquires a transmission image of a vehicle under inspection; an image processing unit that acquires a transmission image template of the same vehicle type as the vehicle from a database, The transmission image of the inspected vehicle and the transmission image template are registered, and the registered transmission image and the registered transmission image template are deviated to obtain a variation of the transmission image of the vehicle with respect to the transmission image template. The area is processed to determine whether the vehicle carries a suspect.
  • the image processing unit extracts internal structure information of the vehicle from the transmission image, integrates external feature information of the vehicle, and retrieves a transmission image template of the vehicle model from a database.
  • the solution of the above embodiment can detect the suspect based on the scanned image of the vehicle, and avoids the problem that the traditional method of detecting the vulnerability and the manual judgment effect is poor, and is important for the auxiliary vehicle security inspection.
  • FIG. 1 shows a schematic diagram of a vehicle inspection system in accordance with an embodiment of the present disclosure:
  • FIG. 2 shows a flow chart of a vehicle inspection method in accordance with an embodiment of the present disclosure
  • FIG. 3 is a schematic diagram describing a process of cropping a vehicle image in a vehicle inspection method according to an embodiment of the present disclosure
  • FIG. 4 is a schematic diagram describing a process of registering a vehicle image in a vehicle inspection method according to an embodiment of the present disclosure
  • FIG. 5 is a schematic diagram describing a process of processing a difference image in a vehicle inspection method according to an embodiment of the present disclosure.
  • references to "one embodiment”, “an embodiment”, “an” or “an” or “an” or “an” or “an” In at least one embodiment.
  • the appearances of the phrase “in one embodiment”, “in the embodiment”, “the” Furthermore, the particular features, structures, or characteristics may be combined in one or more embodiments or examples in any suitable combination and/or sub-combination.
  • the term “and/or” as used herein includes any and all combinations of one or more of the associated listed items.
  • embodiments of the present disclosure propose a vehicle inspection method. After acquiring the transmission image of the inspected vehicle, a transmission image template of the same vehicle type as the vehicle is acquired from the database. Then, the transmission image of the inspected vehicle and the transmission image template are registered, and the registered transmission image and the registered transmission image template are deviated to obtain a transmission image of the vehicle relative to the transmission. The changed area of the image template. Finally, the varying area is processed to determine if the vehicle is carrying a suspect.
  • the above solution can eliminate false detections caused by the imaging environment.
  • not only rigid registration but also elastic registration is performed, which eliminates the stereoscopic deformation problem, making the registration of the template image and the image to be inspected more accurate.
  • special processing is performed on the difference image to resolve false detection problems due to suspects and cargo, stereoscopic deformation, scanning noise, and the like that occur during the difference.
  • the energy/dose of the generating device defining the image to be tested and the template image are as identical as possible, the image noise is low, the image deformation is small, etc., the stricter the condition, the better the subtraction effect.
  • the noise is limited to a certain range, and the two pre-processed images are aligned using rigid registration, and further the elastic registration is used to reduce the influence of the stereoscopic deformation, and then the difference image is post-processed to entrain the object. Classification of misdetected objects caused by goods, three-dimensional deformation, scanning noise, etc., and finally indicating entrainment in the results.
  • FIG. 1 shows a schematic diagram of a vehicle inspection system in accordance with an embodiment of the present disclosure.
  • an inspection system in accordance with an embodiment of the present disclosure involves automated safety inspection of a vehicle using a transmission image.
  • the system shown in FIG. 1 includes a sensing device 110, a radiation imaging system 150, a storage device 120, an image processing unit 140, and a display device 130.
  • sensing device 110 includes one or more sensors, such as CCD devices, etc., for obtaining front face information and external dimensional information of the vehicle, and the like.
  • the sensing device may include a camera for capturing a license plate image of the inspected vehicle; and an identification unit for identifying a license plate number of the inspected vehicle from the license plate image.
  • the sensing device 110 includes a reader that reads the ID of the inspected vehicle from a radio frequency tag carried by the inspected vehicle.
  • the radiation imaging system 150 performs an X-ray scan of the inspected vehicle to obtain an X-ray image of the inspected vehicle.
  • the storage device 120 stores the X-ray image and the vehicle model database in which a transmission image template or the like is stored.
  • the image processing unit 140 retrieves the vehicle model template corresponding to the vehicle from the vehicle model database, and determines a variation region between the obtained transmission image and the transmission template image. Display device 130 presents the changed region to the user.
  • the sensing device 110 obtains a sign image of the vehicle.
  • the corresponding small vehicle can also be identified by the sensing device 110, generating a unique identification ID of the software system and the small vehicle, such as a license plate number.
  • the vehicle unique identification ID is a unique identifier for the small vehicle in the software system.
  • the identification ID may be data generated by the software system for the small vehicle, or may be identified by identifying the license plate number of the vehicle.
  • the current software system is identified by the license plate number.
  • the data processing unit 140 retrieves the template library using the license plate identification to obtain a template image corresponding to the small vehicle to be inspected. A variation region between the obtained transmission image and the template image is determined. Display device 130 presents the changed region to the user.
  • FIG. 2 illustrates a flow chart of a vehicle inspection method in accordance with an embodiment of the present disclosure.
  • a transmission image of the inspected vehicle is acquired.
  • a transmission image template of the same vehicle type as the vehicle is acquired from the database.
  • the two input images (including the image to be tested of the inspected vehicle and the retrieved empty template image) employed in the embodiment of the present disclosure try to select a radiation image of the same device.
  • the image to be tested is generated in real time on the device site, and the template image is acquired in multiple ways, either manually or automatically.
  • Related methods may be, but are not limited to: (1) license plate matching, and the most recent image of the vehicle is found in the historical model image library as a template.
  • the internal structure information of the vehicle is extracted from the scanned transmission image, and the external feature information of the vehicle is integrated, and the transmission image template of the vehicle model is retrieved from the database.
  • the image can be selectively preprocessed. Since the resolution of the radiation image is determined by the scanning device, since the size and width of the small vehicle are different, there are often air regions of different sizes around the vehicle in the scanned image. These air regions not only affect the efficiency of the algorithm, but also the noise may affect the effect of the algorithm.
  • the image is preprocessed in two steps of dividing the vehicle and downsampling.
  • the edge information is used as the main basis.
  • the position of the vehicle in the image is judged, and the smallest rectangle of the vehicle is used as a sub-image for subsequent processing.
  • the schematic diagram of the cutting process is shown in Figure 3.
  • the processing method is divided into three steps: first stripe the stripe to obtain a smooth background image; gradient the image, and quantize the gradient map to remove the small gradient fluctuation effect; in the binary quantized gradient map, find the level The largest continuous area of vertical projection, ie the maximum vehicle position therein.
  • the striping method is: stripping the stripes horizontally and vertically. Taking the level as an example, the projection sequence Proj of the image in the vertical direction is first obtained. For median filtering of Proj, the difference between the filter before and after the filter is judged as a stripe, and the value of this row is replaced with the value of the row of the most recent non-streaked image.
  • the gradient method is: quantizing the image.
  • the quantization level is about 8.
  • the gradient is obtained to obtain the image shown in c of Fig. 3.
  • Find the position of the vehicle Calculate the horizontal and vertical directions of the gradient map, and then reduce the minimum value (that is, remove the influence of the stripes that may still exist), the maximum continuous area. This area is the location of the vehicle. Result of the cut As shown in d of Figure 3.
  • the downsampling process means that the image size is further reduced by downsampling after the image is still too large.
  • the image size is uniformly scaled to a length of 1024 pixels, and the width and the scale of the length are scaled by the same scale.
  • the algorithm time of the size image is within 2 s, and the real-time performance is basically realized.
  • step S23 the transmission image of the inspected vehicle and the transmission image template are registered. Since the image to be tested and the template image have a certain degree of rotation, displacement, geometric deformation, etc., it is obvious that the two images need to be aligned before they are made worse.
  • the gray level of the image is first adjusted to the uniform range by performing the gray level normalization on the basis of the rigid alignment to vertically align the image in size and displacement. Then, using the elastic registration, the two images are subjected to finer nonlinear registration to eliminate the influence of noise such as stereo deformation.
  • Rigid registration is to globally align the image.
  • the flow is as follows: firstly, feature extraction is performed on the two images to obtain feature points; the matching feature point pairs are found by performing similarity measure; then the image space is obtained by matching feature point pairs. Coordinate transformation parameters; finally image registration by coordinate transformation parameters.
  • Feature extraction is the key in registration technology. Accurate feature extraction provides guarantee for the success of feature matching. Seeking feature extraction methods with good invariance and accuracy is crucial for matching accuracy. There are many methods for feature extraction, which are easily understood by the professional, and can also be associated with several alternative algorithms for feature extraction methods.
  • the sift algorithm is selected in the embodiment of the disclosure for feature extraction.
  • the image to be tested is deformed correspondingly to the template image, so that the two images are substantially aligned in displacement and rotation.
  • the sift algorithm is used to extract the features of the image, and then the random sample Consensus (RANSAC) algorithm is used to obtain the deformation parameters.
  • RANSAC random sample Consensus
  • Figure 4 shows the effect of the algorithm.
  • the left picture is the sift feature point correspondence between the image to be tested and the template image.
  • the sift transformed image is basically aligned with the lower left template image to further use the elastic registration algorithm.
  • the gray scale of the image can be normalized and stretched to 0-255.
  • the process can be enhanced by a certain degree of enhancement. Image contrast.
  • the elastic registration of the image is primarily for accurate registration of the image to eliminate local distortion.
  • Elastic registration The methods are mainly divided into two categories: pixel-based methods and feature-based methods. In comparison with the calculation amount, the effectiveness, and the like, preferably, the Demons elastic registration algorithm is selected in the embodiment of the present disclosure to complete this step.
  • step S24 the registered transmission image and the registered transmission image template are evaluated to obtain a variation region of the transmission image of the vehicle with respect to the transmission image template.
  • the difference between the image to be measured and the image of the template image is the difference.
  • Affected by noise the portion of the difference map greater than 0 at this time may be caused by four conditions: entrainment, cargo, vehicle deformation and variation, and other noise.
  • the purpose of the post-treatment is to separate the entrainment in these four cases and obtain the final result. It is easy for the professional to associate with the post-processing of the difference map, such as the size and amplitude of the communication area, the multi-difference pattern fusion involving the dual-energy detection device, the division of the interest region combined with the user interaction, and the assistance according to the atomic number of the substance. Make component judgments, etc.; parameters can be artificially defined or acquired by machine learning.
  • step S25 the varying area is processed to determine if the vehicle is carrying a suspect.
  • FIG. 5 shows the process of processing the difference image.
  • step S51 a difference image is input, and then in step S52, the grayscale is adjusted. Due to the large difference between the input image and the overall gray value of the template image (excluding possible entrainment), the algorithm uses the air gray information of the two images to eliminate the adverse effects caused by this difference, so as to facilitate Binary correctly.
  • step S53 adaptive iterative binarization. Determine the minimum possible value of the binarization threshold according to the histogram of the interpolated image, and eliminate the influence of the goods in the process of binarization by iterative method to perform binarization successively; this can ensure that the entrained area will not be leaked Check or misdetect.
  • step S54 it is judged whether or not a possible cargo area is stored in order to eliminate the cargo area which may exist. If it exists, the goods area is deleted in step S55. In this way, the cargo judgment of the binarized image given for the first time will be excluded in this part of the cargo, which is convenient for detecting the real entrained object.
  • the false binarized area is eliminated. Since the actual acquired image may have spatial rotation distortion and other factors, the binarized region at this time may be a false region caused by the rotational distortion.
  • the algorithm uses the false region to exist in the pair of bright and dark regions. Knowledge, this part of the region has been removed to reduce false detections.
  • step S57 the image area binarized in the air region is eliminated. Due to the detector and other reasons, the acquired image may have a brightening/darkening, a column-by-column brightening/darkening, and an irregular black-and-white variation, so that the detected image and the template image are grayed out in the air region. Values may have significant irregularities
  • the difference in variation leads to possible detector information in the air region in the binarized image; the algorithm uses the neighborhood information of the binarized region and the relevant air threshold empirical knowledge to eliminate this part of the obvious pseudo information.
  • a binarized image is output.
  • the position of the suspect detected by the algorithm may be marked in the image to be tested, which is convenient for the inspection personnel to observe.
  • Another example is to mark the suspect boundary with a curve of a specific color or directly color all the pixels of the suspect area.
  • aspects of the embodiments disclosed herein may be implemented in an integrated circuit as a whole or in part, as one or more of one or more computers running on one or more computers.
  • a computer program eg, implemented as one or more programs running on one or more computer systems
  • implemented as one or more programs running on one or more processors eg, implemented as one or One or more programs running on a plurality of microprocessors, implemented as firmware, or substantially in any combination of the above, and those skilled in the art, in accordance with the present disclosure, will be provided with design circuitry and/or write software and / or firmware code capabilities.
  • signal bearing media include, but are not limited to, recordable media such as floppy disks, hard drives, compact disks (CDs), digital versatile disks (DVDs), digital tapes, computer memories, and the like; and transmission-type media such as digital and / or analog communication media (eg, fiber optic cable, waveguide, wired communication link, wireless communication link, etc.).

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Library & Information Science (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Biochemistry (AREA)
  • Health & Medical Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Geophysics (AREA)
  • General Life Sciences & Earth Sciences (AREA)
  • High Energy & Nuclear Physics (AREA)
  • Quality & Reliability (AREA)
  • Image Analysis (AREA)
  • Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)

Abstract

L'invention concerne un procédé d'inspection de véhicule. Le procédé consiste : à acquérir une image de transmission d'un véhicule inspecté ; à acquérir un modèle d'image de transmission d'un type de véhicule identique à celui du véhicule à partir d'une base de données ; à réaliser un enregistrement sur l'image de transmission du véhicule inspecté et le modèle d'image de transmission ; à obtenir une différence entre une image de transmission après l'enregistrement et un modèle d'image de transmission après l'enregistrement, afin d'obtenir une zone de changement de l'image de transmission du véhicule par rapport au modèle d'image de transmission ; et à traiter la zone de changement afin de déterminer si le véhicule transporte un objet suspect, ce qui permet d'éviter les problèmes de lacune de détection et de performance médiocre lors d'une détermination manuelle d'une image de manière classique et ce qui est important pour aider à l'inspection de sécurité d'un petit véhicule.
PCT/CN2015/098438 2014-12-30 2015-12-23 Procédé et système d'inspection de véhicule WO2016107474A1 (fr)

Priority Applications (3)

Application Number Priority Date Filing Date Title
EP15875152.9A EP3115772B1 (fr) 2014-12-30 2015-12-23 Procédé et système d'inspection de véhicule
MYPI2016703579A MY190242A (en) 2014-12-30 2015-12-23 Vehicle inspection methods and systems
US15/282,134 US10289699B2 (en) 2014-12-30 2016-09-30 Vehicle inspection methods and systems

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201410840660.0 2014-12-30
CN201410840660.0A CN105809655B (zh) 2014-12-30 2014-12-30 车辆检查方法和系统

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US15/282,134 Continuation US10289699B2 (en) 2014-12-30 2016-09-30 Vehicle inspection methods and systems

Publications (1)

Publication Number Publication Date
WO2016107474A1 true WO2016107474A1 (fr) 2016-07-07

Family

ID=56284251

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/098438 WO2016107474A1 (fr) 2014-12-30 2015-12-23 Procédé et système d'inspection de véhicule

Country Status (5)

Country Link
US (1) US10289699B2 (fr)
EP (1) EP3115772B1 (fr)
CN (1) CN105809655B (fr)
MY (1) MY190242A (fr)
WO (1) WO2016107474A1 (fr)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018096355A1 (fr) * 2016-11-28 2018-05-31 Smiths Heimann Sas Détection d'irrégularités à l'aide d'un enregistrement
EP3505972A1 (fr) * 2017-12-26 2019-07-03 Nuctech Company Limited Procédé, appareil et système d'assistance d'inspection de sécurité
CN110930724A (zh) * 2019-12-09 2020-03-27 公安部交通管理科学研究所 基于深度学习的交通非现场违法记录筛选审核方法及系统

Families Citing this family (38)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3764280A1 (fr) * 2016-02-22 2021-01-13 Rapiscan Systems, Inc. Procédés de vérification des types de conteneurs
US10546385B2 (en) * 2016-02-25 2020-01-28 Technion Research & Development Foundation Limited System and method for image capture device pose estimation
US10591277B2 (en) * 2016-07-28 2020-03-17 Liberty Reach Inc. Method and system for measuring outermost dimension of a vehicle positioned at an inspection station
US10809415B2 (en) 2016-08-25 2020-10-20 Beijing Haulixing Technology Development Co., Ltd. Imaging device for use in vehicle security check and method therefor
CN106373124B (zh) * 2016-09-21 2019-01-08 哈尔滨工业大学 基于灰度共生矩阵与ransac的工业产品表面缺陷视觉检测方法
WO2018080425A1 (fr) * 2016-10-24 2018-05-03 Ford Global Technologies, Llc Utilisation de véhicules aériens sans pilote pour inspecter des véhicules autonomes
US10678244B2 (en) 2017-03-23 2020-06-09 Tesla, Inc. Data synthesis for autonomous control systems
US11893393B2 (en) 2017-07-24 2024-02-06 Tesla, Inc. Computational array microprocessor system with hardware arbiter managing memory requests
US11157441B2 (en) 2017-07-24 2021-10-26 Tesla, Inc. Computational array microprocessor system using non-consecutive data formatting
US10671349B2 (en) 2017-07-24 2020-06-02 Tesla, Inc. Accelerated mathematical engine
US11409692B2 (en) 2017-07-24 2022-08-09 Tesla, Inc. Vector computational unit
CN108152051A (zh) * 2017-12-25 2018-06-12 北京华力兴科技发展有限责任公司 移动式车辆底盘检查系统
US11561791B2 (en) 2018-02-01 2023-01-24 Tesla, Inc. Vector computational unit receiving data elements in parallel from a last row of a computational array
US11215999B2 (en) 2018-06-20 2022-01-04 Tesla, Inc. Data pipeline and deep learning system for autonomous driving
US11361457B2 (en) 2018-07-20 2022-06-14 Tesla, Inc. Annotation cross-labeling for autonomous control systems
US11636333B2 (en) 2018-07-26 2023-04-25 Tesla, Inc. Optimizing neural network structures for embedded systems
CN110163056B (zh) * 2018-08-26 2020-09-29 国网江苏省电力有限公司物资分公司 智能视觉识别车板线缆盘中心坐标系统
US11562231B2 (en) 2018-09-03 2023-01-24 Tesla, Inc. Neural networks for embedded devices
CN109446913B (zh) * 2018-09-28 2021-11-05 桂林电子科技大学 一种判断车底是否改装的检测方法
IL282172B2 (en) 2018-10-11 2024-02-01 Tesla Inc Systems and methods for training machine models with enhanced data
US11196678B2 (en) 2018-10-25 2021-12-07 Tesla, Inc. QOS manager for system on a chip communications
US11816585B2 (en) 2018-12-03 2023-11-14 Tesla, Inc. Machine learning models operating at different frequencies for autonomous vehicles
US11537811B2 (en) 2018-12-04 2022-12-27 Tesla, Inc. Enhanced object detection for autonomous vehicles based on field view
US11610117B2 (en) 2018-12-27 2023-03-21 Tesla, Inc. System and method for adapting a neural network model on a hardware platform
US10997461B2 (en) 2019-02-01 2021-05-04 Tesla, Inc. Generating ground truth for machine learning from time series elements
US11567514B2 (en) 2019-02-11 2023-01-31 Tesla, Inc. Autonomous and user controlled vehicle summon to a target
US10956755B2 (en) 2019-02-19 2021-03-23 Tesla, Inc. Estimating object properties using visual image data
DE102019107952B4 (de) * 2019-03-27 2023-08-10 Volume Graphics Gmbh Computer-implementiertes Verfahren zur Analyse von Messdaten eines Objekts
JP7151634B2 (ja) * 2019-06-13 2022-10-12 いすゞ自動車株式会社 点検支援プログラム及び点検支援システム
US11587315B2 (en) 2019-06-19 2023-02-21 Deere & Company Apparatus and methods for augmented reality measuring of equipment
US11580628B2 (en) * 2019-06-19 2023-02-14 Deere & Company Apparatus and methods for augmented reality vehicle condition inspection
US11631283B2 (en) * 2019-06-27 2023-04-18 Toyota Motor North America, Inc. Utilizing mobile video to provide support for vehicle manual, repairs, and usage
CN110285870A (zh) * 2019-07-22 2019-09-27 深圳市卓城科技有限公司 车辆轴型与车轮数检测分析方法及其系统
CN111539260B (zh) * 2020-04-01 2023-08-22 石化盈科信息技术有限责任公司 车辆安检管理方法、装置、存储介质以及系统
CN117092713A (zh) * 2020-05-28 2023-11-21 同方威视技术股份有限公司 建立车辆模板库的方法和系统
CN112633115B (zh) * 2020-12-17 2024-04-05 杭州海康机器人股份有限公司 一种车底携带物检测方法、装置及存储介质
CN114764072A (zh) * 2020-12-31 2022-07-19 同方威视科技（北京）有限公司 车辆检查系统
WO2023069462A2 (fr) * 2021-10-18 2023-04-27 Paolozzi Investments, Inc. Systèmes et procédés de nettoyage contrôlé de véhicules

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6047041A (en) * 1997-09-08 2000-04-04 Scientific Measurement System Apparatus and method for comparison
CN101162204A (zh) * 2006-10-10 2008-04-16 同方威视技术股份有限公司 基于辐射图像变动检测的小型车辆夹带物自动检测方法
CN103338325A (zh) * 2013-06-14 2013-10-02 杭州普维光电技术有限公司 基于全景摄像机的车底盘图像采集方法
CN103984961A (zh) * 2014-05-30 2014-08-13 成都西物信安智能系统有限公司 一种用于检测车底异物的图像检测方法

Family Cites Families (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5031228A (en) * 1988-09-14 1991-07-09 A. C. Nielsen Company Image recognition system and method
US5987159A (en) * 1996-09-24 1999-11-16 Cognex Corporation System or method for detecting defect within a semi-opaque enclosure
US9412142B2 (en) * 2002-08-23 2016-08-09 Federal Law Enforcement Development Services, Inc. Intelligent observation and identification database system
US20050267657A1 (en) * 2004-05-04 2005-12-01 Devdhar Prashant P Method for vehicle classification
SG121906A1 (en) * 2004-10-11 2006-05-26 Stratech Systems Ltd Intelligent vehicle access control system
CA2608119A1 (fr) * 2005-05-11 2006-11-16 Optosecurity Inc. Procede et systeme d'inspection de bagages, de conteneurs de fret ou de personnes
JP5121506B2 (ja) * 2008-02-29 2013-01-16 キヤノン株式会社 画像処理装置、画像処理方法、プログラム及び記憶媒体
US8150105B2 (en) * 2008-05-22 2012-04-03 International Electronic Machines Corporation Inspection using three-dimensional profile information
US8615067B2 (en) * 2009-07-14 2013-12-24 John Hayes Method and apparatus for scanning objects in transit
GB2508565B (en) * 2011-09-07 2016-10-05 Rapiscan Systems Inc X-ray inspection system that integrates manifest data with imaging/detection processing
US20150143913A1 (en) * 2012-01-19 2015-05-28 Purdue Research Foundation Multi-modal sensing for vehicle
CN104567758B (zh) * 2013-10-29 2017-11-17 同方威视技术股份有限公司 立体成像系统及其方法
US20150324885A1 (en) * 2014-05-07 2015-11-12 John Griffin Presenting Service Options Using a Model of a Vehicle
US10324223B2 (en) * 2014-06-24 2019-06-18 Mohammed Al-Hoshani Method, an apparatus, and a system for automated inspection of motorized vehicles
CN105787495A (zh) 2014-12-17 2016-07-20 同方威视技术股份有限公司 具有车辆参考图像检索及比对功能的车辆检查系统和方法
US10223609B2 (en) * 2015-10-02 2019-03-05 The Regents Of The University Of California Passenger vehicle make and model recognition system
US9824453B1 (en) * 2015-10-14 2017-11-21 Allstate Insurance Company Three dimensional image scan for vehicle

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6047041A (en) * 1997-09-08 2000-04-04 Scientific Measurement System Apparatus and method for comparison
CN101162204A (zh) * 2006-10-10 2008-04-16 同方威视技术股份有限公司 基于辐射图像变动检测的小型车辆夹带物自动检测方法
CN103338325A (zh) * 2013-06-14 2013-10-02 杭州普维光电技术有限公司 基于全景摄像机的车底盘图像采集方法
CN103984961A (zh) * 2014-05-30 2014-08-13 成都西物信安智能系统有限公司 一种用于检测车底异物的图像检测方法

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018096355A1 (fr) * 2016-11-28 2018-05-31 Smiths Heimann Sas Détection d'irrégularités à l'aide d'un enregistrement
US11062440B2 (en) 2016-11-28 2021-07-13 Smiths Detection France Sas Detection of irregularities using registration
EP3505972A1 (fr) * 2017-12-26 2019-07-03 Nuctech Company Limited Procédé, appareil et système d'assistance d'inspection de sécurité
US11055869B2 (en) 2017-12-26 2021-07-06 Nuctech Company Limited Security inspection based on scanned images
CN110930724A (zh) * 2019-12-09 2020-03-27 公安部交通管理科学研究所 基于深度学习的交通非现场违法记录筛选审核方法及系统

Also Published As

Publication number Publication date
US20170017667A1 (en) 2017-01-19
EP3115772B1 (fr) 2023-08-16
CN105809655B (zh) 2021-06-29
MY190242A (en) 2022-04-07
CN105809655A (zh) 2016-07-27
EP3115772A1 (fr) 2017-01-11
US10289699B2 (en) 2019-05-14
EP3115772A4 (fr) 2017-11-08

Similar Documents

Publication Publication Date Title
WO2016107474A1 (fr) Procédé et système d'inspection de véhicule
CN109743879B (zh) 一种基于动态红外热像图处理的地下管廊渗漏检测方法
Hou et al. People counting and human detection in a challenging situation
US20140037159A1 (en) Apparatus and method for analyzing lesions in medical image
US9235902B2 (en) Image-based crack quantification
Chierchia et al. PRNU-based detection of small-size image forgeries
WO2016107478A1 (fr) Procédé et système d'inspection de châssis de véhicule
CN103699905B (zh) 一种车牌定位方法及装置
US20170262985A1 (en) Systems and methods for image-based quantification for allergen skin reaction
US20170046835A1 (en) System and method for detecting polyps from learned boundaries
US9208172B2 (en) Method and system for vehicle identification
Choi et al. Vehicle detection from aerial images using local shape information
Qu et al. Detect digital image splicing with visual cues
US20140301608A1 (en) Chemical structure recognition tool
CN109255785A (zh) 一种轴承外观缺陷检测系统
EP3311333B1 (fr) Appariement d'images d'articles postaux avec des descripteurs de singularites du champ de gradient
Ryu et al. Feature-based pothole detection in two-dimensional images
CN111985423A (zh) 活体检测方法、装置、设备及可读存储介质
CN112257667A (zh) 一种小型船只检测方法、装置、电子设备及存储介质
Arunkumar et al. Estimation of vehicle distance based on feature points using monocular vision
MAARIR et al. Building detection from satellite images based on curvature scale space method
EP4160274A1 (fr) Procédé et système d'inspection de véhicule
CN113420716B (zh) 基于改进Yolov3算法的违规行为识别预警的方法
JP2015225462A (ja) 判別装置、判別プログラムおよび判別方法
Singh et al. A Novel System to Monitor Illegal Sand Mining using Contour Mapping and Color based Image Segmentation

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 15875152

Country of ref document: EP

Kind code of ref document: A1

REEP Request for entry into the european phase

Ref document number: 2015875152

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 2015875152

Country of ref document: EP

NENP Non-entry into the national phase

Ref country code: DE